us-sox-expert
Pass
Audited by Gen Agent Trust Hub on Jul 27, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it is designed to process external compliance and audit documentation using file system tools (
Read,Glob,Grep). If this external content contains malicious instructions, they could influence the agent's output, especially when using theWritetool to generate reports or remediation plans. - Ingestion points: File system access via
Read,Glob, andGrepdefined in the skill frontmatter. - Boundary markers: Absent; the instructions do not specify delimiters or instructions to ignore embedded commands in analyzed data.
- Capability inventory: The skill utilizes the
Writecapability to create or modify project files. - Sanitization: Absent; no explicit sanitization or content validation steps are described.
- [NO_CODE]: The skill consists entirely of markdown documentation and natural language instructions. No executable scripts (e.g., Python, JavaScript, Shell) were found.
Audit Metadata